Apparatus, method and storage medium storing program for determining naturalness of array of words

Abstract

An apparatus is provided which determines the naturalness of an array of words as a sentence. When an entire source text to be translated is not registered in a lexicon, the source text is divided into plural words. A parallel translation for each word in the source text is obtained to generate parallel translation patterns, and a web search is made for a text which includes each of the parallel translation patterns (step 36 to 44).

Description

BACKGROUND OF THE INVENTION[0001]1. Field of the Invention[0002]The present invention relates to an apparatus, a method, and a storage medium storing a program for determining the naturalness of an array of words, in particular to an apparatus for determining the naturalness of an array of words which is realized in a computer connected to the Internet, a method for determining the naturalness of an array of words which can be applied to the apparatus for determining the naturalness of an array of words, and a storage medium storing a program for determining the naturalness of an array of words which is implemented in a computer functioning as the apparatus for determining the naturalness of an array of words.[0003]2. Description of the Related Art[0004]A realization of a translation system in which a sentence (source text) described in a natural language (source language) is translated into another sentence (parallel / corresponding translated text) described in another natural langu...

AI Technical Summary

Benefits of technology

[0007]The present invention was made in consideration of the above facts, and one object of the present invention is to provide an apparatus for determining the naturalness of an array of words which can fairly determine the naturalness of an array of words as a sentence, a method for determining the naturalness of an array of words, and a storage medium storing a program for determining the naturalness of an array of words.

Problems solved by technology

However, a parallel translated text which is generated by using the existing automatic translation technology is often an unnatural sentence in a target language even if the parallel translated text does not have any grammatical errors or parallel translation errors in word units, and accuracy in translation for practical use actually has not been achieved yet by the conventional automatic translation technologies including the disclosure of the above-described patent.

However, it is difficult to quantitatively measure the naturalness of a sentence because the measurement relies on sensory indexes, and it is also difficult to define a criterion to determine the naturalness of an array of words, which is generated as a sentence in a target language.

Therefore, a technology to determine the naturalness of an array of words as a sentence which is obtained as a parallel translated text by automatic translation, or an array of words which is manually composed as a sentence by a person, is not yet established.

Images